{"id":"https://openalex.org/W7156265759","doi":"https://doi.org/10.1145/3774904.3792209","title":"Optimizing Multi-Turn Interactive Recommendation Agents via Generative Intrinsic Motivation","display_name":"Optimizing Multi-Turn Interactive Recommendation Agents via Generative Intrinsic Motivation","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7156265759","doi":"https://doi.org/10.1145/3774904.3792209"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792209","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792209","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792209","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101929118","display_name":"Xueyang Feng","orcid":"https://orcid.org/0000-0003-4426-5732"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xueyang Feng","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5595-3775","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043446092","display_name":"Jiakai Tang","orcid":"https://orcid.org/0000-0001-9543-8889"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiakai Tang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9543-8889","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101755392","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0003-0144-1775"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0144-1775","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048783161","display_name":"Quanyu Dai","orcid":"https://orcid.org/0000-0001-7578-2738"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanyu Dai","raw_affiliation_strings":["Huawei Technologies Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7578-2738","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134675662","display_name":"Zhenhua Dong","orcid":"https://orcid.org/0000-0002-2231-4663"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Dong","raw_affiliation_strings":["Huawei Technologies Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2231-4663","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101929118"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96390455,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5975","last_page":"5986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.25859999656677246,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.25859999656677246,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.20469999313354492,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1168999969959259,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6482999920845032},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6083999872207642},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6036999821662903},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5910000205039978},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5497000217437744},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.5131000280380249},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4821000099182129},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3693000078201294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937999963760376},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6482999920845032},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5910000205039978},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5364000201225281},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36239999532699585},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.35679998993873596},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792209","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792209","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792209","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792209","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49011051654815674}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2054141820","https://openalex.org/W2067562626","https://openalex.org/W2970641574","https://openalex.org/W3036394672","https://openalex.org/W3168892396","https://openalex.org/W4386081001","https://openalex.org/W4389524458","https://openalex.org/W4393065402","https://openalex.org/W4402667093","https://openalex.org/W4402670735","https://openalex.org/W4402671853","https://openalex.org/W4402671855","https://openalex.org/W4403221076","https://openalex.org/W4411112982","https://openalex.org/W4412888593","https://openalex.org/W4412991558","https://openalex.org/W4416034969","https://openalex.org/W4416037139","https://openalex.org/W4416146846","https://openalex.org/W7133211372"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,43],"have":[3],"given":[4],"rise":[5],"to":[6,26,44],"interactive":[7,46,80],"recommendation":[8],"agents":[9],"(IRAs).":[10],"Through":[11],"proactive":[12,28],"clarification,":[13],"tool":[14],"invocation,":[15],"and":[16,75],"dynamic":[17],"dialogue,":[18],"IRAs":[19],"shift":[20],"recommender":[21],"systems":[22],"from":[23,49],"passive":[24],"prediction":[25],"interactive,":[27],"intelligence.":[29],"For":[30],"training":[31],"IRAs,":[32],"agentic":[33],"reinforcement":[34],"learning":[35,77],"offers":[36],"a":[37],"natural":[38],"pathway,":[39],"as":[40],"it":[41],"enables":[42],"learn":[45],"capabilities":[47],"directly":[48],"environmental":[50],"feedback":[51],"without":[52],"requiring":[53],"costly":[54],"annotated":[55],"data.":[56],"However,":[57],"this":[58],"process":[59],"faces":[60],"three":[61],"key":[62],"challenges:":[63],"credit":[64],"assignment":[65],"in":[66,71],"multi-turn":[67],"interactions,":[68],"efficient":[69],"exploration":[70],"large":[72],"action":[73],"spaces,":[74],"coordinated":[76],"of":[78],"multiple":[79],"skills.":[81]},"counts_by_year":[],"updated_date":"2026-04-28T06:12:00.211691","created_date":"2026-04-28T00:00:00"}